基于CT的胰腺分割深度学习模型比较
该回顾性研究在352例CT扫描上基准测试了五种胰腺分割模型,以Dice评分、Hausdorff距离和平均表面距离评估,并按对比剂状态和胰周衰减四分位数分层。TS、AAUNet和AASwin表现最佳(Dice分别为80±11%、79±16%、77±18%,两两Sidak检验无显著差异),DM-UNet最差(Dice=67±16%)。除TS外,所有算法Dice评分随胰周衰减增加而降低(P<.01)。
要点
- TS、AAUNet、AASwin胰腺分割表现最佳,Dice分别为80±11%、79±16%、77±18%,两两无显著差异。
- AASwin和MSD-nnUNet在平扫CT上所有指标均差于增强CT(P<.001)。
- 除TS外,所有算法Dice评分随胰周衰减增加而降低(P<.01)。
核心结论
- 基于卷积神经网络的模型(TS、AAUNet、AASwin)在多样化扫描集上表现最佳;TS仅用13%的训练集大小(8488 vs 1204扫描)即达到与AAUNet和AASwin相当的性能。
研究设计与样本
- 回顾性研究,通过PubMed和ArXiv检索识别五种胰腺分割模型,在352例标注CT扫描(2000-2023年,30例女性、25例男性、297例性别未知;年龄58±7岁[±1 SD],327例年龄未知)上评估。
诊断标准与关键数值
- 评估指标为Dice评分、Hausdorff距离(HD)和平均表面距离(ASD),按对比剂状态和胰周5 mm区域衰减四分位数分层;多变量回归分析9项影像特征和生物标志物与Dice评分的关联。
临床应用与阅片要点
- TS、AAUNet和AASwin整体分割性能最佳且两两无显著差异;平扫CT上AASwin和MSD-nnUNet性能下降(P<.001);除TS外所有算法Dice随胰周衰减增加而降低(P<.01)。
局限性
- 本研究为回顾性研究。
- 评估数据集中297例性别未知、327例年龄未知。
- 其他文献中胰腺分割算法的汇总评估指标不足以反映临床人群中常见患者和扫描特征下的差异性能。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Pancreas segmentation accuracy at CT is critical for the identification of pancreatic pathologies and is essential for the development of imaging biomarkers. Our objective was to benchmark the performance of five high-performing pancreas segmentation models across multiple metrics stratified by scan and patient/pancreatic characteristics that may affect segmentation performance.
MATERIALS AND METHODS: In this retrospective study, PubMed and ArXiv searches were conducted to identify pancreas segmentation models which were then evaluated on a set of annotated imaging datasets. Results (Dice score, Hausdorff distance [HD], average surface distance [ASD]) were stratified by contrast status and quartiles of peri-pancreatic attenuation (5 mm region around pancreas). Multivariate regression was performed to identify imaging characteristics and biomarkers (n = 9) that were significantly associated with Dice score.
RESULTS: Five pancreas segmentation models were identified: Abdomen Atlas [AAUNet, AASwin, trained on 8448 scans], TotalSegmentator [TS, 1204 scans], nnUNetv1 [MSD-nnUNet, 282 scans], and a U-Net based model for predicting diabetes [DM-UNet, 427 scans]. These were evaluated on 352 CT scans (30 females, 25 males, 297 sex unknown; age 58 ± 7 years [ ± 1 SD], 327 age unknown) from 2000-2023. Overall, TS, AAUNet, and AASwin were the best performers, Dice= 80 ± 11%, 79 ± 16%, and 77 ± 18%, respectively (pairwise Sidak test not-significantly different). AASwin and MSD-nnUNet performed worse (for all metrics) on non-contrast scans (vs contrast, P < .001). The worst performer was DM-UNet (Dice=67 ± 16%). All algorithms except TS showed lower Dice scores with increasing peri-pancreatic attenuation (P < .01). Multivariate regression showed non-contrast scans, (P < .001; MSD-nnUNet), smaller pancreatic length (P = .005, MSD-nnUNet), and height (P = .003, DM-UNet) were associated with lower Dice scores.
CONCLUSION: The convolutional neural network-based models trained on a diverse set of scans performed best (TS, AAUnet, and AASwin). TS performed equivalently to AAUnet and AASwin with only 13% of the training set size (8488 vs 1204 scans). Though trained on the same dataset, a transformer network (AASwin) had poorer performance on non-contrast scans whereas its convolutional network counterpart (AAUNet) did not. This study highlights how aggregate assessment metrics of pancreatic segmentation algorithms seen in other literature are not enough to capture differential performance across common patient and scanning characteristics in clinical populations.
引用
- Suri A, Mukherjee P, Pickhardt PJ, et al. A Comparison of CT-Based Pancreatic Segmentation Deep Learning Models. Acad Radiol. 2024. PMID: 38944630. doi:10.1016/j.acra.2024.06.015
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。